Pub Date : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862052
Muthumeenakshi Subramanian, B. Geethanjali, N. Seshadri, V. Bhavana, R. Vijayalakshmi
Attention is the primary cognitive process to induce a response to a stimulus. Maintaining the attentive state continuously for a prolonged period of time is known as sustained attention which is vital for performing any task. The present study aims at evaluating the activation of different brain regions while performing an attention requiring task. A standard attention task called the Visual Continuous Performance test was employed for the study. The analysis is achieved with the help of electroencephalography (EEG) recorded simultaneously during the entire period of execution of task. The task report detailing the errors committed, reaction time is generated automatically and indicates the level of performance. The relative theta and gamma power were significantly higher (p=0.05) during task when compared to that determined during rest, whereas in alpha band the relative power was significantly higher (p=0.05) during rest when compared to task. Event related synchronization (ERS) and Event related Desynchronization (ERD) in relative theta power and relative alpha power respectively was observed particularly in the parietal cognitive processing electrodes (associated with attention). Theta synchronisation and alpha desynchronization is associated with good performance; this was supported by the task performance result which reported a minimum of errors. These event-related changes helped sustain attention and a visualization of the activated brain regions was accomplished for a better depiction of the findings.
{"title":"Visualization of brain activation during the performance of attention-demanding tasks","authors":"Muthumeenakshi Subramanian, B. Geethanjali, N. Seshadri, V. Bhavana, R. Vijayalakshmi","doi":"10.1109/ICCI-CC.2016.7862052","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862052","url":null,"abstract":"Attention is the primary cognitive process to induce a response to a stimulus. Maintaining the attentive state continuously for a prolonged period of time is known as sustained attention which is vital for performing any task. The present study aims at evaluating the activation of different brain regions while performing an attention requiring task. A standard attention task called the Visual Continuous Performance test was employed for the study. The analysis is achieved with the help of electroencephalography (EEG) recorded simultaneously during the entire period of execution of task. The task report detailing the errors committed, reaction time is generated automatically and indicates the level of performance. The relative theta and gamma power were significantly higher (p=0.05) during task when compared to that determined during rest, whereas in alpha band the relative power was significantly higher (p=0.05) during rest when compared to task. Event related synchronization (ERS) and Event related Desynchronization (ERD) in relative theta power and relative alpha power respectively was observed particularly in the parietal cognitive processing electrodes (associated with attention). Theta synchronisation and alpha desynchronization is associated with good performance; this was supported by the task performance result which reported a minimum of errors. These event-related changes helped sustain attention and a visualization of the activated brain regions was accomplished for a better depiction of the findings.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127866559","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862033
H. Hiraishi
This paper describes a qualitative analysis of the concentration level required to throw an object at a specific target, such as the free throw in basketball or darts games, using a simple brain-wave sensor that is a type of electroencephalograph. The qualitative analysis does not focus on quantity, but on qualitative changes, such as increasing, decreasing, or stabilizing. The analysis allows us to clarify the essential features of subjects where standards are individually different, such as brain waves or concentration levels. Therefore, we analyze the differences in concentration levels between experts and novices while throwing. Furthermore, we analyze the influence of concentration levels by pre-performance routines (PPRs), which involve performing certain determined motions before throwing, and are often executed in sports for the purpose of removing stress or raising concentration. The analysis reveals a concentration-stabilizing phenomenon where the concentration level becomes stabilized prior to throwing. We also find that the phenomenon appears more conspicuously in the case of experts and PPRs. This means that a type of PPR exists in the case of experts, and removing stress or raising concentration, both of which are the purpose of PPRs, is similar to stabilizing the concentration gained from brain waves. Therefore, because we can train PPRs by checking the concentration levels, we designed a PPR training tool that uses smart glass, one of the wearable computers.
{"title":"Qualitative analysis of pre-performance routines in throwing using simple brain-wave sensor","authors":"H. Hiraishi","doi":"10.1109/ICCI-CC.2016.7862033","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862033","url":null,"abstract":"This paper describes a qualitative analysis of the concentration level required to throw an object at a specific target, such as the free throw in basketball or darts games, using a simple brain-wave sensor that is a type of electroencephalograph. The qualitative analysis does not focus on quantity, but on qualitative changes, such as increasing, decreasing, or stabilizing. The analysis allows us to clarify the essential features of subjects where standards are individually different, such as brain waves or concentration levels. Therefore, we analyze the differences in concentration levels between experts and novices while throwing. Furthermore, we analyze the influence of concentration levels by pre-performance routines (PPRs), which involve performing certain determined motions before throwing, and are often executed in sports for the purpose of removing stress or raising concentration. The analysis reveals a concentration-stabilizing phenomenon where the concentration level becomes stabilized prior to throwing. We also find that the phenomenon appears more conspicuously in the case of experts and PPRs. This means that a type of PPR exists in the case of experts, and removing stress or raising concentration, both of which are the purpose of PPRs, is similar to stabilizing the concentration gained from brain waves. Therefore, because we can train PPRs by checking the concentration levels, we designed a PPR training tool that uses smart glass, one of the wearable computers.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114382751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862025
Glavin Wiechert, Matt Triff, Zhixing Liu, Zhicheng Yin, Shuai Zhao, Ziyun Zhong, Runxing Zhaou, P. Lingras
This paper studies the supervised classification of electroencephalogram (EEG) brain signals to identify persons and their activities. The brain signals are obtained from a commercially available and modestly priced wearable headband. Such wearable devices generate a large amount of data and due to their attractive pricing structure are becoming increasingly commonplace. As a result, the data generated from such wearables will increase exponentially leading to many interesting data mining opportunities. We propose a representation that reduces variable length signals to a more manageable and uniformly fixed length distributions. These fixed length distributions can then be used with a variety of data mining techniques. The experiments with a number of classification techniques, including decision trees, SVM, neural networks, and random forests show that it is possible to identify both the persons and the activities with a reasonable degree of precision.
{"title":"Identifying users and activities with cognitive signal processing from a wearable headband","authors":"Glavin Wiechert, Matt Triff, Zhixing Liu, Zhicheng Yin, Shuai Zhao, Ziyun Zhong, Runxing Zhaou, P. Lingras","doi":"10.1109/ICCI-CC.2016.7862025","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862025","url":null,"abstract":"This paper studies the supervised classification of electroencephalogram (EEG) brain signals to identify persons and their activities. The brain signals are obtained from a commercially available and modestly priced wearable headband. Such wearable devices generate a large amount of data and due to their attractive pricing structure are becoming increasingly commonplace. As a result, the data generated from such wearables will increase exponentially leading to many interesting data mining opportunities. We propose a representation that reduces variable length signals to a more manageable and uniformly fixed length distributions. These fixed length distributions can then be used with a variety of data mining techniques. The experiments with a number of classification techniques, including decision trees, SVM, neural networks, and random forests show that it is possible to identify both the persons and the activities with a reasonable degree of precision.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123454682","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862032
Baris Nasir, F. Yarman-Vural
In this paper, we introduce graph simplification capabilities of a new tool, CEREBRA, which is used to visualize the 3D network of human brain, extracted from the fMRI data. The nodes of the network are defined as the voxels with the attributes corresponding to the intensity values changing by time and the coordinates in three dimensional Euclidean space. The arc weights are estimated by modeling the relationships among the voxel activation records. We aim to help researchers to reveal the underlying brain state by examining the active regions of the brain and observe the interactions among them. Although the tool provides many features for displaying the fMRI data as a dynamical network, in this study, we have mainly focused on two main features. The first one is the unique graph simplification module that allows users to eliminate redundant edges according to some weighted similarity criterion. The second one is visualizing the output of the external algorithms for voxel selection, clustering or network representation of fMRI data. Thus, users are able to display, analyze and further process the output of their own algorithms.
{"title":"Simplification and visualization of brain network extracted from fMRI data using CEREBRA","authors":"Baris Nasir, F. Yarman-Vural","doi":"10.1109/ICCI-CC.2016.7862032","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862032","url":null,"abstract":"In this paper, we introduce graph simplification capabilities of a new tool, CEREBRA, which is used to visualize the 3D network of human brain, extracted from the fMRI data. The nodes of the network are defined as the voxels with the attributes corresponding to the intensity values changing by time and the coordinates in three dimensional Euclidean space. The arc weights are estimated by modeling the relationships among the voxel activation records. We aim to help researchers to reveal the underlying brain state by examining the active regions of the brain and observe the interactions among them. Although the tool provides many features for displaying the fMRI data as a dynamical network, in this study, we have mainly focused on two main features. The first one is the unique graph simplification module that allows users to eliminate redundant edges according to some weighted similarity criterion. The second one is visualizing the output of the external algorithms for voxel selection, clustering or network representation of fMRI data. Thus, users are able to display, analyze and further process the output of their own algorithms.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123594149","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862065
M. T. Chan, Christine W. Chan, Craig M. Gelowitz
This paper presents Racer, a car-racing simulator where the human player races a car against three game-controlled cars in a three-dimensional environment. The game incorporates artificial intelligence (AI) techniques, and the objective of AI in video games is not to defeat the human player, but to provide the player with a challenging and enjoyable experience. The game is a software simulation that incorporates considerations of human driving behavior. The paper provides a brief history of AI techniques in games, presents the use of AI techniques in contemporary video games, and discusses the contemporary video game AI techniques that were implemented in the development of Racer.
{"title":"Development of a cognitive vehicle system for simulation of driving behavior","authors":"M. T. Chan, Christine W. Chan, Craig M. Gelowitz","doi":"10.1109/ICCI-CC.2016.7862065","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862065","url":null,"abstract":"This paper presents Racer, a car-racing simulator where the human player races a car against three game-controlled cars in a three-dimensional environment. The game incorporates artificial intelligence (AI) techniques, and the objective of AI in video games is not to defeat the human player, but to provide the player with a challenging and enjoyable experience. The game is a software simulation that incorporates considerations of human driving behavior. The paper provides a brief history of AI techniques in games, presents the use of AI techniques in contemporary video games, and discusses the contemporary video game AI techniques that were implemented in the development of Racer.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125909234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862072
Lixiao Feng, Jun Peng, Guorong Chen, Chengyuan Chen, Dedong Tang
The research of the communication between medical implanted electronic devices (hereinafter referred to as implanted devices) and external devices is a focus. In this paper, a data communications model based Volume Conduction is presented. As the frequency increases the KHz level, the effect of background biological noise is considered negligible, the channel is thus modeled as the additive white Gaussian noise (AWGN) channel in these frequencies. From Shannon information theory, in two-dimensional modulation, the volume conduction channel capacity formula was derived, further derivation: with extremely low signal to noise ratio (SNR) using in the two-level modulation can be very effective use of channel capacity, with high SNR a multi-level modulation is used in order to make full use of the channel capacity. System-view software is used to the channel simulation, the input and output signal waveforms and eye diagram comparison, the curves of the BER (bit error rate) and SNR.
{"title":"Communication channel analysis and simulation of medical implanted electronic devices based on the volume conduction","authors":"Lixiao Feng, Jun Peng, Guorong Chen, Chengyuan Chen, Dedong Tang","doi":"10.1109/ICCI-CC.2016.7862072","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862072","url":null,"abstract":"The research of the communication between medical implanted electronic devices (hereinafter referred to as implanted devices) and external devices is a focus. In this paper, a data communications model based Volume Conduction is presented. As the frequency increases the KHz level, the effect of background biological noise is considered negligible, the channel is thus modeled as the additive white Gaussian noise (AWGN) channel in these frequencies. From Shannon information theory, in two-dimensional modulation, the volume conduction channel capacity formula was derived, further derivation: with extremely low signal to noise ratio (SNR) using in the two-level modulation can be very effective use of channel capacity, with high SNR a multi-level modulation is used in order to make full use of the channel capacity. System-view software is used to the channel simulation, the input and output signal waveforms and eye diagram comparison, the curves of the BER (bit error rate) and SNR.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129782037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862059
M. Pineres, D. A. Diaz, D. Josyula, B. JovaniA.Jiménez
Metacognition has been used in artificial intelligence to increase the level of autonomy of intelligent systems. However the design of systems with metacognitive skills is a difficult task due to the number and complexity of processes involved. This paper describes a MOF-based visual metacognitive modeling tool named MetaThink. MetaThink has a core based on a metacognitive metamodel named MISM. MetaThink was validated using the Tracing technique and the metacognitive models obtained from the validation process were consistent with MISM.
{"title":"MetaThink: A MOF-based metacognitive modeling tool","authors":"M. Pineres, D. A. Diaz, D. Josyula, B. JovaniA.Jiménez","doi":"10.1109/ICCI-CC.2016.7862059","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862059","url":null,"abstract":"Metacognition has been used in artificial intelligence to increase the level of autonomy of intelligent systems. However the design of systems with metacognitive skills is a difficult task due to the number and complexity of processes involved. This paper describes a MOF-based visual metacognitive modeling tool named MetaThink. MetaThink has a core based on a metacognitive metamodel named MISM. MetaThink was validated using the Tracing technique and the metacognitive models obtained from the validation process were consistent with MISM.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130792935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862035
Arman Afrasiyabi, Itir Önal, F. Yarman-Vural
One of the major drawbacks of brain decoding from the functional magnetic resonance images (fMRI) is the very high dimension of feature space which consists of thousands of voxels in sequence of brain volumes, recorded during a cognitive stimulus. In this study, we propose a new architecture, called Sparse Temporal Mesh Model (STMM), which reduces the dimension of the feature space by combining the voxel selection methods with the mesh learning method. We, first, select the “most discriminative” voxels using the state-of-the-art feature selection methods, namely, Recursive Feature Elimination (RFE), one way Analysis of Variance (ANOVA) and Mutual Information (MI). After we select the most informative voxels, we form a star mesh around each selected voxel with their functional neighbors. Then, we estimate the mesh arc weights, which represent the relationship among the voxels within a neighborhood. We further prune the estimated arc weights using ANOVA to get rid of redundant relationships among the voxels. By doing so, we obtain a sparse representation of information in the brain to discriminate cognitive states. Finally, we train k-Nearest Neighbor (kNN) and Support Vector Machine (SVM) classifiers by the feature vectors of sparse mesh arc weights. We test STMM architecture on a visual object recognition experiment. Our results show that forming meshes around the selected voxels leads to a substantial increase in the classification accuracy, compared to forming meshes around all the voxels in the brain. Furthermore, pruning the mesh arc weights by ANOVA solves the dimensionality curse problem and leads to a slight increase in the classification performance. We also discover that, the resulting network of sparse temporal meshes are quite similar in all three voxel selection methods, namely, RFE, ANOVA or MI.
{"title":"A Sparse Temporal Mesh Model for brain decoding","authors":"Arman Afrasiyabi, Itir Önal, F. Yarman-Vural","doi":"10.1109/ICCI-CC.2016.7862035","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862035","url":null,"abstract":"One of the major drawbacks of brain decoding from the functional magnetic resonance images (fMRI) is the very high dimension of feature space which consists of thousands of voxels in sequence of brain volumes, recorded during a cognitive stimulus. In this study, we propose a new architecture, called Sparse Temporal Mesh Model (STMM), which reduces the dimension of the feature space by combining the voxel selection methods with the mesh learning method. We, first, select the “most discriminative” voxels using the state-of-the-art feature selection methods, namely, Recursive Feature Elimination (RFE), one way Analysis of Variance (ANOVA) and Mutual Information (MI). After we select the most informative voxels, we form a star mesh around each selected voxel with their functional neighbors. Then, we estimate the mesh arc weights, which represent the relationship among the voxels within a neighborhood. We further prune the estimated arc weights using ANOVA to get rid of redundant relationships among the voxels. By doing so, we obtain a sparse representation of information in the brain to discriminate cognitive states. Finally, we train k-Nearest Neighbor (kNN) and Support Vector Machine (SVM) classifiers by the feature vectors of sparse mesh arc weights. We test STMM architecture on a visual object recognition experiment. Our results show that forming meshes around the selected voxels leads to a substantial increase in the classification accuracy, compared to forming meshes around all the voxels in the brain. Furthermore, pruning the mesh arc weights by ANOVA solves the dimensionality curse problem and leads to a slight increase in the classification performance. We also discover that, the resulting network of sparse temporal meshes are quite similar in all three voxel selection methods, namely, RFE, ANOVA or MI.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126502078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862023
Makoto Oide, Akiko Takahashi, Toru Abe, T. Suganuma
We propose a method to determine appropriate quality of service (QoS) dynamically required by users for video streaming services in this paper. In the proposed method, the QoS parameters for the video streaming are determined based on the machine learning algorithm, by using a regression analysis in particular, according to the user requirements, computational/network resources and service provisioning environments. In this paper, we describe the design and implementation of our method. Furthermore, we confirm the feasibility of our proposed method through an experiment of a prototype system.
{"title":"Design and implementation of user-oriented video streaming service based on machine learning","authors":"Makoto Oide, Akiko Takahashi, Toru Abe, T. Suganuma","doi":"10.1109/ICCI-CC.2016.7862023","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862023","url":null,"abstract":"We propose a method to determine appropriate quality of service (QoS) dynamically required by users for video streaming services in this paper. In the proposed method, the QoS parameters for the video streaming are determined based on the machine learning algorithm, by using a regression analysis in particular, according to the user requirements, computational/network resources and service provisioning environments. In this paper, we describe the design and implementation of our method. Furthermore, we confirm the feasibility of our proposed method through an experiment of a prototype system.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122700141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-08-01DOI: 10.1109/ICCI-CC.2016.7862095
Yingxu Wang
Recent basic studies reveal that AI problems are deeply rooted in both the understanding of the natural intelligence and the adoption of suitable mathematical means for rigorously modeling the brain in machine understandable forms. Learning is a cognitive process of knowledge and behavior acquisition. Learning can be classified into five categories known as object identification, cluster classification, functional regression, behavior generation, and knowledge acquisition. A fundamental challenge to knowledge learning different from the deep and recurring neural network technologies has led to the emergence of the field of cognitive machine learning on the basis of recent breakthroughs in denotational mathematics and mathematical engineering. This keynote lecture presents latest advances in formal brain studies and cognitive systems for deep reasoning and deep learning. It is recognized that key technologies enabling cognitive robots mimicking the brain rely not only on deep learning, but also on deep reasoning and thinking towards machinable thoughts and cognitive knowledge bases built by a cognitive systems. A fundamental theory and novel technology for implementing deep thinking robots are demonstrated based on concept algebra, semantics algebra, and inference algebra.
{"title":"Deep reasoning and thinking beyond deep learning by cognitive robots and brain-inspired systems","authors":"Yingxu Wang","doi":"10.1109/ICCI-CC.2016.7862095","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2016.7862095","url":null,"abstract":"Recent basic studies reveal that AI problems are deeply rooted in both the understanding of the natural intelligence and the adoption of suitable mathematical means for rigorously modeling the brain in machine understandable forms. Learning is a cognitive process of knowledge and behavior acquisition. Learning can be classified into five categories known as object identification, cluster classification, functional regression, behavior generation, and knowledge acquisition. A fundamental challenge to knowledge learning different from the deep and recurring neural network technologies has led to the emergence of the field of cognitive machine learning on the basis of recent breakthroughs in denotational mathematics and mathematical engineering. This keynote lecture presents latest advances in formal brain studies and cognitive systems for deep reasoning and deep learning. It is recognized that key technologies enabling cognitive robots mimicking the brain rely not only on deep learning, but also on deep reasoning and thinking towards machinable thoughts and cognitive knowledge bases built by a cognitive systems. A fundamental theory and novel technology for implementing deep thinking robots are demonstrated based on concept algebra, semantics algebra, and inference algebra.","PeriodicalId":135701,"journal":{"name":"2016 IEEE 15th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134441742","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：